|
--- |
|
license: cc-by-nc-4.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-IEMOCAP_5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# videomae-base-finetuned-IEMOCAP_5 |
|
|
|
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3229 |
|
- Accuracy: 0.3770 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- training_steps: 4280 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.3642 | 0.1 | 429 | 1.4078 | 0.1970 | |
|
| 1.3244 | 1.1 | 858 | 1.4578 | 0.3052 | |
|
| 1.3623 | 2.1 | 1287 | 1.4071 | 0.2314 | |
|
| 1.3422 | 3.1 | 1716 | 1.3474 | 0.2896 | |
|
| 1.2483 | 4.1 | 2145 | 1.3597 | 0.3127 | |
|
| 1.3581 | 5.1 | 2574 | 1.3512 | 0.2639 | |
|
| 1.3106 | 6.1 | 3003 | 1.3295 | 0.2896 | |
|
| 1.341 | 7.1 | 3432 | 1.3132 | 0.3433 | |
|
| 1.2438 | 8.1 | 3861 | 1.2732 | 0.3859 | |
|
| 1.2438 | 9.1 | 4280 | 1.2643 | 0.3715 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
